Add LiteRT converted swinv2_small_window8_256

f0b384c verified 23 days ago

1.87 kB

library_name: litert
base_model: timm/swinv2_small_window8_256.ms_in1k
tags:
  - vision
  - image-classification
datasets:
  - imagenet-1k

swinv2_small_window8_256

Converted TIMM image classification model for LiteRT.

Source architecture: swinv2_small_window8_256
Source checkpoint: timm/swinv2_small_window8_256.ms_in1k
File: model.tflite
Input: float32 tensor in NCHW layout, shape [1, 3, 256, 256]
Output: ImageNet-1K logits, shape [1, 1000]

Runtime Status

CPU smoke test: passed with LiteRT CompiledModel.
GPU delegation: currently blocked for this model by rank-5 tensor patterns in the GPU backend, mostly RESHAPE, TRANSPOSE, and related window/attention operations. The model is published as CPU-ready while GPU support is being improved.

Model Details

Model Type: Image classification / feature backbone
Model Stats:
- Params (M): 49.7
- GMACs: 11.6
- Activations (M): 40.1
- Image size: 256 x 256
Papers:
- Swin Transformer V2: Scaling Up Capacity and Resolution: https://arxiv.org/abs/2111.09883
Original: https://github.com/microsoft/Swin-Transformer
Dataset: ImageNet-1k

Citation

@inproceedings{liu2021swinv2,
  title={Swin Transformer V2: Scaling Up Capacity and Resolution}, 
  author={Ze Liu and Han Hu and Yutong Lin and Zhuliang Yao and Zhenda Xie and Yixuan Wei and Jia Ning and Yue Cao and Zheng Zhang and Li Dong and Furu Wei and Baining Guo},
  booktitle={International Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2022}
}

@misc{rw2019timm,
  author = {Ross Wightman},
  title = {PyTorch Image Models},
  year = {2019},
  publisher = {GitHub},
  journal = {GitHub repository},
  doi = {10.5281/zenodo.4414861},
  howpublished = {\url{https://github.com/huggingface/pytorch-image-models}}
}